© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36106
    Prev
    Next
    INDEX
    Explanations

    constructor definitions and destructors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aident
    -1.13
    Isolated
    -1.10
     honnête
    -1.03
    伤口
    -0.99
     flesta
    -0.98
     asumi
    -0.95
    kehren
    -0.94
     samt
    -0.94
    tiler
    -0.94
    einer
    -0.94
    POSITIVE LOGITS
    ’
    1.08
     ?',
    0.99
    Last
    0.91
     Petru
    0.91
    tablissements
    0.90
     will
    0.89
    ⁉
    0.88
    $?
    0.88
    kg
    0.87
     >",
    0.87
    Activations Density 0.001%

    No Known Activations